EmptyDroplets (FDR <= 0.1) + scDblFindersetwd("/media/jacopo/Elements/re_align/MM/PRJNA732205/SAMN19314102/SRR14629342/")
# Load the libraries (from Sarah script + biomart)
library(tidyverse) # packages for data wrangling, visualization etc
library(Seurat) # scRNA-Seq analysis package
library(clustree) # plot of clustering tree
library(ggsignif) # Enrich your 'ggplots' with group-wise comparisons
library(clusterProfiler) #The package implements methods to analyze and visualize functional profiles of gene and gene clusters.
library(org.Hs.eg.db) # Human annotation package neede for clusterProfiler
library(ggrepel) # extra geoms for ggplo2
library(patchwork) #multiplots
library(reticulate)
Load and do the QC for the cellranger data
#list.files(".")
dat <- Read10X(data.dir ="./out/counts_filtered/")
dat <- CreateSeuratObject(dat) # Create the seurat object from the 10x data
kb.initial <- dat@assays[["RNA"]]@counts@Dim[[2]]
cat("Initial number of cells:", kb.initial,
"\nNumber of genes:", dat@assays[["RNA"]]@counts@Dim[[1]])
## Initial number of cells: 2087
## Number of genes: 36601
Empty cells were already filtered, check for % mt RNA and death markers:
# first calculate the mitochondrial percentage for each cell
dat$percent_mt <- PercentageFeatureSet(dat, pattern="^MT.")
# make violin plots
mt_rna = 20
max_counts = 30000
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
VlnPlot(dat, features = c("nCount_RNA", "nFeature_RNA", "percent_mt")) + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot1 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "percent_mt")
plot1 <- plot1 + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot2 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "nFeature_RNA")
plot2 <- plot2 + geom_vline(xintercept = max_counts, linetype = "dotted")
plot1
plot2
## cells retained by mt RNA content ( 20 %): 1581
## percentage of retained cells: 75.75 %
## cells retained by counts ( 30000 ): 1579
## percentage of retained cells: 75.66 %
Check the distribution of the cells with low counts and control death markers:
min_counts = 350
hist(dat@meta.data$nCount_RNA, breaks = 100, xlab = "Counts")
hist(dat@meta.data$nCount_RNA, breaks = 1000, xlab = "Counts", xlim = c(0,5000))
hist(dat@meta.data$nCount_RNA, breaks = 10000, xlab = "Counts", xlim = c(0,1000))
abline(v=min_counts, col="red", lty = 3)
The evident peak of cells with < 200 counts could contain dying
cells.
# Subset the dataset to focus only on those cells with low counts
dat.lowcount <- subset(dat, subset = nCount_RNA < min_counts)
# Get the mean of the counts for each gene and sort them decreasing
meanCounts <- rowMeans(GetAssayData(object = dat.lowcount, slot = 'counts'))
meanCounts <- sort(meanCounts, decreasing = T)
# A boxplot can help to observe the distribution of the means
#boxplot(meanCounts)
# Print the most highly expressed genes
head(meanCounts, 30)
## IGLC1 MALAT1 IGHG3 IGKC IGHGP MT-ND2 MT-CO2
## 45.7241379 24.2758621 9.8448276 8.8275862 6.3793103 3.1724138 1.8965517
## MT-CO3 IGHG1 MT-ND4 MT-ND1 MT-ND3 MT-CYB MTRNR2L12
## 1.8103448 1.7758621 1.5344828 1.3620690 1.3275862 1.3275862 1.2068966
## MT-ATP6 MT-CO1 IGHG2 RPS18 B2M RPLP1 SSR4
## 1.1379310 1.0172414 0.8965517 0.7758621 0.7586207 0.7586207 0.6896552
## RPL41 Z93241.1 MT-ND5 RPLP2 RPL13 RPL13A TPT1
## 0.6551724 0.6034483 0.5862069 0.5517241 0.5517241 0.5344828 0.4827586
## RPL10 MZB1
## 0.4827586 0.4482759
## cells retained by counts ( 350 ): 1521
## percentage of retained cells: 72.88 %
dir.create("result")
saveRDS(dat, file = "./result/SAMN19314102_clean_QC.Rds")
#Normalize
dat <- NormalizeData(dat)
# Find the first 4000 variabe features
dat <- FindVariableFeatures(dat, selection.method = "vst", nfeatures = 4000)
Set mean expression to 0 and variance across 1 to avoid highly expressed genes drive the forwarding analyses. Since negative expression is meaningless, scaled data are useful only for UMAP and clustering
# scale data, the scaled data are saved in:
# dat[["RNA"]]@scale.data
all.genes <- rownames(dat)
dat <- ScaleData(dat, vars.to.regress = c("percent_mt","nCount_RNA"))
dat <- RunPCA(dat, features = VariableFeatures(object = dat), verbose = F, seed.use = 1)
print(dat[["pca"]], dims = 1:5, nfeatures = 5)
## PC_ 1
## Positive: IER2, NEAT1, TIMP1, RASD1, ID2
## Negative: RPS12, RPL13, RPS25, RPL19, SEC61G
## PC_ 2
## Positive: PRDX1, HERPUD1, PSAT1, GLRX, PSMB1
## Negative: RPS19, RPLP2, RPS18, RPL13A, RPL34
## PC_ 3
## Positive: IGKC, IGHGP, IGHG1, IGHG2, SSR4
## Negative: S100A4, NMI, RNF130, ZEB2, CAT
## PC_ 4
## Positive: IGKC, ITM2C, EEF1A1, TMEM59, EEF1G
## Negative: JUN, HIST1H2BG, AL021155.5, Z93241.1, HSPB1
## PC_ 5
## Positive: FTL, SRGN, TMSB4X, IER2, S100A10
## Negative: RPL13, IGHGP, RPS12, IGHG1, IGHG2
UMAP is a graph-based method of clustering. The first step in this process is to construct a KNN graph based on the euclidean distance in PCA space:
dat <- FindNeighbors(dat, dims = 1:20)
The graph now can be used as input for the function
runUMAP()
dat <- RunUMAP(dat, dims = 1:20, seed.use = 1)
DimPlot(dat, reduction = 'umap', seed = 1)
## QC metrics
## markers